Search Results for author:
Found 35 papers, 16 papers with code
Improving Multimodal Interactive Agents with Reinforcement Learning from Human Feedback
Here we demonstrate how to use reinforcement learning from human feedback (RLHF) to improve upon simulated, embodied agents trained to a base level of competency with imitation learning.
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
BIG-bench focuses on tasks that are believed to be beyond the capabilities of current language models.
Intra-agent speech permits zero-shot task acquisition
Human language learners are exposed to a trickle of informative, context-sensitive language, but a flood of raw sensory data.
Evaluating Multimodal Interactive Agents
Creating agents that can interact naturally with humans is a common goal in artificial intelligence (AI) research.
Data Distributional Properties Drive Emergent In-Context Learning in Transformers
In further experiments, we found that naturalistic data distributions were only able to elicit in-context learning in transformers, and not in recurrent models.
A data-driven approach for learning to control computers
It would be useful for machines to use computers as humans do so that they can aid us in everyday tasks.
Tell me why! Explanations support learning relational and causal structure
Inferring the abstract relational and causal structure of the world is a major challenge for reinforcement-learning (RL) agents.
Creating Multimodal Interactive Agents with Imitation and Self-Supervised Learning
A common vision from science fiction is that robots will one day inhabit our physical spaces, sense the world as we do, assist our physical labours, and communicate with us through natural language.
Tell me why!—Explanations support learning relational and causal structure
Explanations play a considerable role in human learning, especially in areas that remain major challenges for AI—forming abstractions, and learning about the relational and causal structure of the world.
Synthetic Returns for Long-Term Credit Assignment
We propose state-associative (SA) learning, where the agent learns associations between states and arbitrarily distant future rewards, then propagates credit directly between the two.
Symbolic Behaviour in Artificial Intelligence
This approach will allow for AI to interpret something as symbolic on its own rather than simply manipulate things that are only symbols to human onlookers, and thus will ultimately lead to AI with more human-like symbolic fluency.
Neural spatio-temporal reasoning with object-centric self-supervised learning
Transformer-based language models have proved capable of rudimentary symbolic reasoning, underlining the effectiveness of applying self-attention computations to sets of discrete entities.
Attention over learned object embeddings enables complex visual reasoning
Neural networks have achieved success in a wide array of perceptual tasks but often fail at tasks involving both perception and higher-level reasoning.
Ranked #4 on
Video Object Tracking
on CATER
Imitating Interactive Intelligence
These evaluations convincingly demonstrate that interactive training and auxiliary losses improve agent behaviour beyond what is achieved by supervised learning of actions alone.
Rapid Task-Solving in Novel Environments
We show that EPNs learn to execute a value iteration-like planning algorithm and that they generalize to situations beyond their training experience.
Automated curriculum generation through setter-solver interactions
We demonstrate the success of our approach in rich but sparsely rewarding 2D and 3D environments, where an agent is tasked to achieve a single goal selected from a set of possible goals that varies between episodes, and identify challenges for future work.
Environmental drivers of systematicity and generalization in a situated agent
The question of whether deep neural networks are good at generalising beyond their immediate training experience is of critical importance for learning-based approaches to AI.
Automated curricula through setter-solver interactions
We demonstrate the success of our approach in rich but sparsely rewarding 2D and 3D environments, where an agent is tasked to achieve a single goal selected from a set of possible goals that varies between episodes, and identify challenges for future work.
Deep reinforcement learning with relational inductive biases
We introduce an approach for augmenting model-free deep reinforcement learning agents with a mechanism for relational reasoning over structured representations, which improves performance, learning efficiency, generalization, and interpretability.
Is coding a relevant metaphor for building AI? A commentary on "Is coding a relevant metaphor for the brain?", by Romain Brette
Brette contends that the neural coding metaphor is an invalid basis for theories of what the brain does.
Learning to Make Analogies by Contrasting Abstract Relational Structure
Here, we study how analogical reasoning can be induced in neural networks that learn to perceive and reason about raw visual data.
An investigation of model-free planning
The field of reinforcement learning (RL) is facing increasingly challenging domains with combinatorial complexity.
Learning Visual Question Answering by Bootstrapping Hard Attention
Attention mechanisms in biological perception are thought to select subsets of perceptual information for more sophisticated processing which would be prohibitive to perform on all sensory inputs.
Ranked #7 on
Visual Question Answering (VQA)
on CLEVR
Assessing the Scalability of Biologically-Motivated Deep Learning Algorithms and Architectures
Here we present results on scaling up biologically motivated models of deep learning on datasets which need deep networks with appropriate architectures to achieve good performance.
Measuring abstract reasoning in neural networks
To succeed at this challenge, models must cope with various generalisation `regimes' in which the training and test data differ in clearly-defined ways.
Relational Deep Reinforcement Learning
We introduce an approach for deep reinforcement learning (RL) that improves upon the efficiency, generalization capacity, and interpretability of conventional approaches through structured perception and relational reasoning.
Relational recurrent neural networks
Memory-based neural networks model temporal data by leveraging an ability to remember information for long periods.
Ranked #66 on
Language Modelling
on WikiText-103
Relational inductive biases, deep learning, and graph networks
As a companion to this paper, we have released an open-source software library for building graph networks, with demonstrations of how to use them in practice.
Hyperbolic Attention Networks
We introduce hyperbolic attention networks to endow neural networks with enough capacity to match the complexity of data with hierarchical and power-law structure.
Unsupervised Predictive Memory in a Goal-Directed Agent
Animals execute goal-directed behaviours despite the limited range and scope of their sensors.
Cognitive Psychology for Deep Neural Networks: A Shape Bias Case Study
To explore the potential value of these tools, we chose a well-established analysis from developmental psychology that explains how children learn word labels for objects, and applied that analysis to DNNs.
A simple neural network module for relational reasoning
Relational reasoning is a central component of generally intelligent behavior, but has proven difficult for neural networks to learn.
Image Retrieval with Multi-Modal Query
Question Answering
+2
Discovering objects and their relations from entangled scene representations
We show that RNs are capable of learning object relations from scene description data.
Generative Temporal Models with Memory
We consider the general problem of modeling temporal data with long-range dependencies, wherein new observations are fully or partially predictable based on temporally-distant, past observations.
One-shot Learning with Memory-Augmented Neural Networks
Despite recent breakthroughs in the applications of deep neural networks, one setting that presents a persistent challenge is that of "one-shot learning."
